{"id":"W4205753857","doi":"10.1016/j.artmed.2022.102243","title":"ResAttenGAN: Simultaneous segmentation of multiple spinal structures on axial lumbar MRI image using residual attention and adversarial learning","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Overfitting; Computer science; Artificial intelligence; Discriminative model; Segmentation; Feature (linguistics); Pattern recognition (psychology); Residual; Pixel; Feature learning; Image segmentation; Computer vision; Artificial neural network; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005663614,0.0001325347,0.0002529292,0.0002704229,0.0001553432,0.0000120245,0.0001026711,0.0000397255,0.0002140167],"category_scores_gemma":[0.0006622145,0.0001297044,0.00003244294,0.0003892642,0.0001841539,0.00006819762,0.00004170612,0.0004727191,0.000002376479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008850258,"about_ca_system_score_gemma":0.0000148737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006050344,"about_ca_topic_score_gemma":0.00005401051,"domain_scores_codex":[0.9984718,0.0001482134,0.0004978416,0.0002247947,0.0004533974,0.0002039358],"domain_scores_gemma":[0.9995025,0.0002034802,0.00008517064,0.0001067676,0.00003785659,0.00006415707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001067867,0.00003217121,0.001524139,0.00005621319,0.00002907277,0.00006610106,0.001750539,0.6571093,0.2729469,0.0001612806,0.00003270995,0.06618487],"study_design_scores_gemma":[0.0001884026,0.0003040454,0.0005180477,0.0001019766,0.00005574781,0.00001141881,0.009943316,0.9735736,0.0141579,0.0009640203,0.00003530409,0.0001462129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9643067,0.0001451935,0.03462469,0.0002402163,0.0004414209,0.000127122,0.000004664337,0.0000496288,0.00006043381],"genre_scores_gemma":[0.9981061,0.00005083919,0.001434342,0.00003336072,0.0003143835,0.000005611264,0.00002731766,0.00001702226,0.00001097522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3164644,"threshold_uncertainty_score":0.5289193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03094076602719397,"score_gpt":0.3112021803132757,"score_spread":0.2802614142860818,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}